{"id":"W4405220551","doi":"10.1016/j.ijhcs.2024.103434","title":"Human performance effects of combining counterfactual explanations with normative and contrastive explanations in supervised machine learning for automated decision assistance","year":2024,"lang":"en","type":"article","venue":"International Journal of Human-Computer Studies","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Counterfactual thinking; Normative; Artificial intelligence; Machine learning; Computer science; Psychology; Cognitive psychology; Social psychology; Epistemology; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006240034,0.0008910401,0.0004935817,0.0004457286,0.0003067264,0.001119601,0.0007918318,0.001350139,0.003342659],"category_scores_gemma":[0.05259714,0.0004545451,0.0005605999,0.0002098023,0.000745193,0.001497981,0.001095026,0.000936654,0.0003916292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000437544,"about_ca_system_score_gemma":0.0005804443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006831901,"about_ca_topic_score_gemma":0.001043168,"domain_scores_codex":[0.9960176,0.002349468,0.0003878718,0.0006519486,0.0004479427,0.000145009],"domain_scores_gemma":[0.8999167,0.08753494,0.005157609,0.004375712,0.001971553,0.001043469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.03873766,0.009563772,0.1520393,0.003348178,0.0008866617,0.0007000805,0.01866153,0.03827978,0.1704853,0.002765173,0.00265008,0.5618824],"study_design_scores_gemma":[0.004062776,0.04758322,0.3929257,0.0007125241,0.002372004,0.001551917,0.004723406,0.3565165,0.1551484,0.0204069,0.01320601,0.0007907484],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903917,0.0001457857,0.008116147,0.0001358882,0.0000279582,0.0001291455,0.00006682383,0.0002449046,0.0007416038],"genre_scores_gemma":[0.9808368,0.00006081482,0.01836004,0.00006220033,0.00002299291,0.0001378369,0.0001443246,0.00002000158,0.0003549143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006240034,"threshold_uncertainty_score":0.03300089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02792114798258858,"score_gpt":0.3354367388189123,"score_spread":0.3075155908363237,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}